Desert Plants Recognition by Bark Texture

Recognition of the desert plants is a challenging task for human as well as computers due to the similarities between these plants. We propose a novel method for recognizing of desert plants by the images of the bark. We extract the features of the texture of the bark using Weber Local Descriptor (WLD), we build a dataset of bark images for desert plants, this dataset consists of 1660 bark images for five species of the desert plants, these species are Palm Dates, Mimosa Scabrella, Sidr, Lemon and Pomegranate. We test three classifiers ANN, SVM and KNN on this dataset and the resulted accuracies are 99.7%, 98.8% and 98.0%, respectively. Performance of ANN is very high when compared to SVM and KNN classifiers, hence ANN can be adapted for recognition of the desert plants.